camenduru / emage

EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling (Updated 1 year, 2 months ago)

  • Public
  • 107 runs
  • GitHub
  • Paper
  • License
Iterate in playground
Run with an API
Playground API Examples README Versions

Want to make some of these yourself?

Run this model